Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    problem solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ँ
    0.44
    uação
    0.40
     მიმო
    0.39
    깎
    0.39
    忤
    0.38
    灾
    0.36
    ophagy
    0.36
     Injuries
    0.36
    ClkInitStruct
    0.36
    ungunya
    0.35
    POSITIVE LOGITS
     solve
    3.80
     solving
    3.77
     solved
    3.50
     solves
    3.47
     Solving
    3.45
    solve
    3.44
    Solving
    3.36
     Solve
    3.34
    Solve
    3.23
    solving
    3.16
    Act Density 0.170%

    No Known Activations